Related papers: FocusTune: Tuning Visual Localization through Focu…

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale…

The reduced cost and computational and calibration requirements of monocular cameras make them ideal positioning sensors for mobile robots, albeit at the expense of any meaningful depth measurement. Solutions proposed by some scholars to…

Inspired by human driving focus, this research pioneers networks augmented with Focusing Sampling, Partial Field of View Evaluation, Enhanced FPN architecture and Directional IoU Loss - targeted innovations addressing obstacles to precise…

Key-point-based scene understanding is fundamental for autonomous driving applications. At the same time, optical flow plays an important role in many vision tasks. However, due to the implicit bias of equal attention on all points, classic…

Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an…

Accurately detecting 3D objects from monocular images in dynamic roadside scenarios remains a challenging problem due to varying camera perspectives and unpredictable scene conditions. This paper introduces a two-stage training strategy to…

Current visual foundation models are trained purely on unstructured 2D data, limiting their understanding of 3D structure of objects and scenes. In this work, we show that fine-tuning on 3D-aware data improves the quality of emerging…

The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by…

A major focus of current research on place recognition is visual localization for autonomous driving. In this scenario, as cameras will be operating continuously, it is realistic to expect videos as an input to visual localization…

Research into dynamic 3D scene understanding has primarily focused on short-term change tracking from dense observations, while little attention has been paid to long-term changes with sparse observations. We address this gap with MoRE, a…

Methods tackling multi-object tracking need to estimate the number of targets in the sensing area as well as to estimate their continuous state. While the majority of existing methods focus on data association, precise state (3D pose)…

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…

Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in…

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for…

Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…

We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network (CNN) for first retrieving similar database images and then predicting the relative…

Clustering is the task of gathering similar data samples into clusters without using any predefined labels. It has been widely studied in machine learning literature, and recent advancements in deep learning have revived interest in this…

This paper provides a simple solution for reliably solving image classification tasks tied to spatial locations of salient objects in the scene. Unlike conventional image classification approaches that are designed to be invariant to…